Data from: Early prediction of in-hospital mortality in patients with congestive heart failure in intensive care unit: a retrospective observational cohort study
Han, Didi et al. (2022), Data from: Early prediction of in-hospital mortality in patients with congestive heart failure in intensive care unit: a retrospective observational cohort study, Dryad, Dataset, https://doi.org/10.5061/dryad.tx95x6b18
Objective: Congestive heart failure (CHF) is a clinical syndrome in which heart disease progresses to a severe stage. Risk assessment and early diagnosis of death in patients with CHF are critical to patient prognosis and treatment. The purpose of this study was to establish a nomogram predicting in-hospital death for CHF patients in the ICU.
Design: A retrospective observational cohort study.
Setting and participants: The data of study from 30,411 CHF patients in the Medical Information Mart for Intensive Care (MIMIC-IV) database and the eICU Collaborative Research Database (eICU-CRD).
Primary outcome: In-hospital mortality.
Results: The inclusion criteria were met by 15983 subjects, whose in-hospital mortality rate was 12.4%. Multivariate analysis determined that the independent risk factors were age, race, norepinephrine, dopamine, phenylephrine, vasopressin, mechanical ventilation, intubation, HepF, heart rate, respiratory rate, temperature, SBP, AG, BUN, creatinine, chloride, MCV, RDW, and WBC. The C-index of the nomogram (0.767, 95%CI: 0.759–0.779) was superior to that of the traditional SOFA, APSIII and GWTGHF score, indicating its discrimination power. Calibration plots demonstrated that the predicted results are in good agreement with the observed results. The decision curves of the derivation and validation sets both had net benefits.
Conclusion: The twenty independent risk factors for in-hospital mortality of CHF patients were age, race, norepinephrine, dopamine, phenylephrine, vasopressin, mechanical ventilation, intubation, HepF, heart rate, respiratory rate, temperature, SBP, AG, BUN, creatinine, chloride, MCV, RDW, and WBC. The nomogram that included these factors accurately predicted the in-hospital mortality of CHF patients. The novel nomogram has the potential to be a clinical practice aided predictive tool for predicting and assessing mortality in CHF patients in the ICU.
Univariate logistic regression analysis were used to select risk factors associated with the in-hospital mortality of CHF patients, and multivariate logistic regression was used to build the prediction model. The discrimination, calibration and clinical validity of the model were evaluated by AUC, calibration curve, Hosmer-Lemeshow χ2 test and DCA curve, respectively. Finally, data from 15,503 CHF patients in the multi-center eICU-CRD were used for external validation of the established nomogram.
This Excel contains all the original data analyzed in this study.